paddlespeech.t2s.audio.audio module

class paddlespeech.t2s.audio.audio.AudioProcessor(sample_rate: int, n_fft: int, win_length: int, hop_length: int, n_mels: int = 80, fmin: int = 0, fmax: Optional[int] = None, window='hann', center=True, pad_mode='reflect', normalize=True)[source]

Bases: object

Methods

istft

mel_spectrogram

read_wav

spectrogram

stft

write_wav
istft(D)[source]
mel_spectrogram(wav)[source]
read_wav(filename)[source]
spectrogram(wav)[source]
stft(wav)[source]
write_wav(path, wav)[source]